© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7762
    Prev
    Next
    INDEX
    Explanations

    Aquarius zodiac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Croatian
    -0.08
    ilage
    -0.07
     Bourg
    -0.07
     seguro
    -0.07
     Jackson
    -0.07
     Anglican
    -0.07
     Barbados
    -0.07
     österreich
    -0.07
     noget
    -0.07
     divisions
    -0.07
    POSITIVE LOGITS
    ERRIDE
    0.08
    URLConnection
    0.08
    ouri
    0.08
    noopener
    0.08
     soci
    0.08
    .peek
    0.08
    #+#+
    0.07
    Supplement
    0.07
     adi
    0.07
    Bottle
    0.07
    Activations Density 0.001%

    No Known Activations